Antenna Optimization Method Based on Multi-Knowledge Embedded Artificial Neural Network for Ultra-Wideband Phased Array

In this paper, an antenna optimization method based on multi-knowledge embedded artificial neural network (ANN) for ultra-wideband phased array antenna is presented. The array is based on the tightly coupled dipole array (TCDA) antenna, which is composed of a large number of antenna parameters to be optimized. When considering the beam scanning requirement, it becomes a multi-parameter and multi-objective optimization problem. The mul-ti-knowledge embedded ANN based optimization method is proposed to address this problem. It transforms the complex optimization model into two simple sub-models embedded with the prior knowledge models. The S-parameter transfer function of feedline is regarded as the prior knowledge in the Sub-Model-1, when the equivalent circuit model of the tightly coupled dipole and wide-angle impedance matching layers is regarded as the prior knowledge in the Sub-Model-2. An error matrix is introduced to correct the inaccuracies arising from the cascading of sub-models. This is equivalent to transforming a high-dimensional problem into two low-er-dimensional problems, which reduces the sample space size by several orders of magnitude and enables the effectiveness of the full frequency band and key frequency band optimization of the structurally complex TCDA antenna.